I the possibility to create an MCP server for an observability utility to be able to present the AI agent with dynamic code evaluation capabilities. Due to its potential to rework purposes, MCP is a expertise I’m much more ecstatic about than I initially was about genAI basically. I wrote extra about that and a few intro to MCPs basically in a earlier submit.
Whereas an preliminary POCs demonstrated that there was an immense potential for this to be a pressure multiplier to our product’s worth, it took a number of iterations and a number of other stumbles to ship on that promise. On this submit, I’ll attempt to seize a few of the classes discovered, as I feel that this could profit different MCP server builders.
My Stack
- I used to be utilizing Cursor and vscode intermittently as the primary MCP shopper
- To develop the MCP server itself, I used the .NET MCP SDK, as I made a decision to host the server on one other service written in .NET
Lesson 1: Don’t dump your whole knowledge on the agent
In my utility, one software returns aggregated data on errors and exceptions. The API could be very detailed because it serves a posh UI view, and spews out massive quantities of deeply linked knowledge:
- Error frames
- Affected endpoints
- Stack traces
- Precedence and traits
- Histograms
My first hunch was to easily expose the API as is as an MCP software. In any case, the agent ought to have the ability to make extra sense of it than any UI view, and catch on to attention-grabbing particulars or connections between occasions. There have been a number of situations I had in thoughts as to how I’d count on this knowledge to be helpful. The agent might routinely supply fixes for current exceptions recorded in manufacturing or within the testing setting, let me find out about errors that stand out, or assist me handle some systematic issues which are the underlying root reason behind the problems.
The fundamental premise was subsequently to permit the agent to work its ‘magic’, with extra knowledge probably that means extra hooks for the agent to latch on in its investigation efforts. I shortly coded a wrapper round our API on the MCP endpoint and determined to begin with a primary immediate to see whether or not every thing is working:
We are able to see the agent was sensible sufficient to know that it wanted to name one other software to seize the setting ID for that ‘take a look at’ setting I discussed. With that at hand, after discovering that there was truly no current exception within the final 24 hours, it then took the freedom to scan a extra prolonged time interval, and that is when issues bought somewhat bizarre:
What a wierd response. The agent queries for exceptions from the final seven days, will get again some tangible outcomes this time, and but proceeds to ramble on as if ignoring the information altogether. It continues to try to use the software in numerous methods and completely different parameter combos, clearly fumbling, till I discover it flat out calls out the truth that the information is totally invisible to it. Whereas errors are being despatched again within the response, the agent truly claims there are no errors. What’s going on?
After some investigation, the issue was revealed to be the truth that we’ve merely reached a cap within the agent’s capability to course of massive quantities of information within the response.
I used an present API that was extraordinarily verbose, which I initially even thought of to be a bonus. The top consequence, nevertheless, was that I one way or the other managed to overwhelm the mannequin. Total, there have been round 360k characters and 16k phrases within the response JSON. This consists of name stacks, error frames, and references. This ought to have been supported simply by wanting on the context window restrict for the mannequin I used to be utilizing (Claude 3.7 Sonnet ought to assist as much as 200k tokens), however however the big knowledge dump left the agent completely stumped.
One technique can be to alter the mannequin to at least one that helps a fair larger context window. I converted to the Gemini 2.5 professional mannequin simply to check that principle out, because it boasts an outrageous restrict of 1 million tokens. Positive sufficient, the identical question now yielded a way more clever response:
That is nice! The agent was in a position to parse the errors and discover the systematic reason behind a lot of them with some primary reasoning. Nonetheless, we will’t depend on the consumer utilizing a selected mannequin, and to complicate issues, this was output from a comparatively low bandwidth testing setting. What if the dataset have been even bigger?
To unravel this difficulty, I made some basic modifications to how the API was structured:
- Nested knowledge hierarchy: Hold the preliminary response targeted on high-level particulars and aggregations. Create a separate API to retrieve the decision stacks of particular frames as wanted.
- Improve queryability: All the queries made thus far by the agent used a really small web page dimension for the information (10), if we would like the agent to have the ability to to entry extra related subsets of the information to suit with the constraints of its context, we have to present extra APIs to question errors primarily based on completely different dimensions, for instance: affected strategies, error kind, precedence and affect and so forth.
With the brand new modifications, the software now persistently analyzes essential new exceptions and comes up with repair solutions. Nonetheless, I glanced over one other minor element I wanted to type earlier than I might actually use it reliably.
Lesson 2: What’s the time?
The keen-eyed reader could have seen that within the earlier instance, to retrieve the errors in a selected time vary, the agent makes use of the ISO 8601 time length format as an alternative of the particular dates and occasions. So as an alternative of together with commonplace ‘From’ and ‘To’ parameters with datetime values, the AI despatched a length worth, for instance, seven days or P7D, to point it needs to examine for errors previously week.
The explanation for that is considerably unusual — the agent may not know the present date and time! You may confirm that your self by asking the agent that easy query. The beneath would have made sense have been it not for the truth that I typed that immediate in at round midday on Could 4th…
Utilizing time length values turned out to be an ideal answer that the agent dealt with fairly nicely. Don’t overlook to doc the anticipated worth and instance syntax within the software parameter description, although!
Lesson 3: When the agent makes a mistake, present it how one can do higher
Within the first instance, I used to be truly greatly surprised by how the agent was in a position to decipher the dependencies between the completely different software calls In an effort to present the fitting setting identifier. In learning the MCP contract, it discovered that it needed to name on a dependent one other software to get the checklist of setting IDs first.
Nonetheless, responding to different requests, the agent would generally take the setting names talked about within the immediate verbatim. For instance, I seen that in response to this query: evaluate sluggish traces for this methodology between the take a look at and prod environments, are there any important variations? Relying on the context, the agent would generally use the setting names talked about within the request and would ship the strings “take a look at” and “prod” because the setting ID.
In my unique implementation, my MCP server would silently fail on this situation, returning an empty response. The agent, upon receiving no knowledge or a generic error, would merely give up and attempt to remedy the request utilizing one other technique. To offset that conduct, I shortly modified my implementation in order that if an incorrect worth was supplied, the JSON response would describe precisely what went mistaken, and even present a sound checklist of attainable values to save lots of the agent one other software name.
This was sufficient for the agent, studying from its mistake, it repeated the decision with the proper worth and one way or the other additionally prevented making that very same error sooner or later.
Lesson 4: Concentrate on consumer intent and never performance
Whereas it’s tempting to easily describe what the API is doing, generally the generic phrases don’t fairly permit the agent to appreciate the kind of necessities for which this performance may apply greatest.
Let’s take a easy instance: My MCP server has a software that, for every methodology, endpoint, or code location, can point out the way it’s getting used at runtime. Particularly, it makes use of the tracing knowledge to point which utility flows attain the particular operate or methodology.
The unique documentation merely described this performance:
[McpServerTool,
Description(
@"For this method, see which runtime flows in the application
(including other microservices and code not in this project)
use this function or method.
This data is based on analyzing distributed tracing.")]
public static async Job GetUsagesForMethod(IMcpService shopper,
[Description("The environment id to check for usages")]
string environmentId,
[Description("The name of the class. Provide only the class name without the namespace prefix.")]
string codeClass,
[Description("The name of the method to check, must specify a specific method to check")]
string codeMethod) The above represents a functionally correct description of what this software does, nevertheless it doesn’t essentially make it clear what varieties of actions it is likely to be related for. After seeing that the agent wasn’t selecting this software up for numerous prompts I believed it will be pretty helpful for, I made a decision to rewrite the software description, this time emphasizing the use instances:
[McpServerTool,
Description(
@"Find out what is the how a specific code location is being used and by
which other services/code.
Useful in order to detect possible breaking changes, to check whether
the generated code will fit the current usages,
to generate tests based on the runtime usage of this method,
or to check for related issues on the endpoints triggering this code
after any change to ensure it didnt impact it"Updating the text helped the agent realize why the information was useful. For example, before making this change, the agent would not even trigger the tool in response to a prompt similar to the one below. Now, it has become completely seamless, without the user having to directly mention that this tool should be used:
Lesson 5: Document your JSON responses
The JSON standard, at least officially, does not support comments. That means that if the JSON is all the agent has to go on, it might be missing some clues about the context of the data you’re returning. For example, in my aggregated error response, I returned the following score object:
"Score": {"Score":21,
"ScoreParams":{ "Occurrences":1,
"Trend":0,
"Recent":20,
"Unhandled":0,
"Unexpected":0}}Without proper documentation, any non-clairvoyant agent would be hard pressed to make sense of what these numbers mean. Thankfully, it is easy to add a comment element at the beginning of the JSON file with additional information about the data provided:
"_comment": "Each error contains a link to the error trace,
which can be retrieved using the GetTrace tool,
information about the affected endpoints the code and the
relevant stacktrace.
Each error in the list represents numerous instances
of the same error and is given a score after its been
prioritized.
The score reflects the criticality of the error.
The number is between 0 and 100 and is comprised of several
parameters, each can contribute to the error criticality,
all are normalized in relation to the system
and the other methods.
The score parameters value represents its contributation to the
overall score, they include:
1. 'Occurrences', representing the number of instances of this error
compared to others.
2. 'Trend' whether this error is escalating in its
frequency.
3. 'Unhandled' represents whether this error is caught
internally or poropagates all the way
out of the endpoint scope
4. 'Unexpected' are errors that are in high probability
bugs, for example NullPointerExcetion or
KeyNotFound",
"EnvironmentErrors":[]This allows the agent to elucidate to the consumer what the rating means in the event that they ask, but additionally feed this clarification into its personal reasoning and proposals.
Selecting the best structure: SSE vs STDIO,
There are two architectures you should use in creating an MCP server. The extra frequent and extensively supported implementation is making your server obtainable as a command triggered by the MCP shopper. This may very well be any CLI-triggered command; npx, docker, and python are some frequent examples. On this configuration, all communication is completed through the method STDIO, and the method itself is working on the shopper machine. The shopper is chargeable for instantiating and sustaining the lifecycle of the MCP server.
This client-side structure has one main disadvantage from my perspective: Because the MCP server implementation is run by the shopper on the native machine, it’s a lot more durable to roll out updates or new capabilities. Even when that downside is one way or the other solved, the tight coupling between the MCP server and the backend APIs it is determined by in our purposes would additional complicate this mannequin by way of versioning and ahead/backward compatibility.
For these causes, I selected the second kind of MCP Server — an SSE Server hosted as part of our utility companies. This removes any friction from working CLI instructions on the shopper machine, in addition to permits me to replace and model the MCP server code together with the applying code that it consumes. On this situation, the shopper is supplied with a URL of the SSE endpoint with which it interacts. Whereas not all purchasers at present assist this selection, there’s a sensible commandMCP known as supergateway that can be utilized as a proxy to the SSE server implementation. Which means customers can nonetheless add the extra extensively supported STDIO variant and nonetheless devour the performance hosted in your SSE backend.
MCPs are nonetheless new
There are lots of extra classes and nuances to utilizing this deceptively easy expertise. I’ve discovered that there’s a massive hole between implementing a workable MCP to at least one that may truly combine with consumer wants and utilization situations, even past these you’ve anticipated. Hopefully, because the expertise matures, we’ll see extra posts on Greatest Practices.
Wish to Join? You may attain me on Twitter at @doppleware or through LinkedIn.
Comply with my mcp for dynamic code evaluation utilizing observability at https://github.com/digma-ai/digma-mcp-server
