Provides the ability to export the call graph to Mermaid format for visualization.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@codegraph-mcp What would break if I change queue.ts?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that indexes a TypeScript/JavaScript codebase into a real call graph and import graph — using TypeScript's own type checker for symbol resolution, not regex or text matching — and exposes it to Claude (or any MCP client) as queryable tools.
Ask Claude things like:
"What would break if I change queue.ts?"
"Who calls createUser?"
"Show me the dependency graph of this module."
Instead of Claude re-reading your whole codebase to answer, it gets a precise, structural answer from a pre-built graph.
No paid APIs, no paid services. Free npm registry / GitHub used only for testing against real-world code (see below).
Code-intelligence tools that build a persistent, queryable graph of a codebase are one of the fastest-moving categories in AI developer tooling right now — this is a scoped-down, honestly-documented version of that idea, built to demonstrate the underlying technique rather than compete with the production tools in that space (see Limitations below).
Related MCP server: vue-ts-lsp
Naive versions of this idea use regex or text matching to find function
calls — which breaks constantly (a call inside a comment, a variable that
happens to share a name with a function, an imported name that shadows a
local one). This project instead uses the real TypeScript compiler API:
it builds an actual ts.Program, asks the type checker to resolve every
call expression to its true declaration, and only records an edge when that
resolution succeeds.
This caught a real, non-obvious bug during development: when an identifier
comes from an import { x } from "...", the checker initially returns an
alias symbol pointing at the import binding itself, not the original
declaration — resolving through that alias (checker.getAliasedSymbol) is
what makes cross-file call resolution actually work. Without that step, only
same-file calls would ever be found. See src/parser.ts for the fix.
On a hand-written 3-file fixture (test/fixtures/sample-project) — full
automated test suite, 20/20 passing, including cross-file resolution:
--- Call edges (the hard part: cross-file resolution via the type checker) ---
PASS: handleSignup calls createUser (CROSS-FILE — requires alias resolution)
PASS: main calls handleSignup (CROSS-FILE — requires alias resolution)
PASS: createUser calls hashPassword (same-file)
PASS: Exactly 3 call edges (no false positives)
--- Query engine ---
PASS: findCallers(createUser) returns exactly handleSignup
PASS: impactAnalysis(userService.ts) finds index.ts at depth 2 (TRANSITIVE, not direct)
20 passed, 0 failedOn a real, published open-source library (sindresorhus/p-queue, a well-known ~2,000-star npm package) — indexed live via the actual MCP tool call, not a script:
Indexed 5 file(s): 32 symbol(s), 7 call edge(s), 7 import edge(s).with a correctly resolved summary — lowerBound (a binary-search helper)
shown being called from within PriorityQueue.enqueue, and queue.ts
correctly identified as the most depended-on file (3 dependents) — matching
p-queue's actual architecture. This also caught a second real bug: p-queue's
source uses ESM-style imports with explicit .js extensions
(import x from './priority-queue.js') even though the real file on disk is
.ts — extremely common in modern TypeScript/NodeNext projects. The
resolver now handles that extension swap; see src/parser.ts.
Tool | Description |
| Parse a codebase into a graph. Run this first. |
| Find where a symbol is defined, by name |
| Who calls a given symbol (cross-file aware) |
| What a given symbol calls |
| Direct import relationships for a file |
| Transitive closure of files affected by changing a file |
| Stats: most-called symbols, most-depended-on files |
git clone https://github.com/SiwarKhalfaoui/codegraph-mcp.git
cd codegraph-mcp
npm install
npm run buildnode build/cli.js index /path/to/some/project/src
node build/cli.js summary
node build/cli.js find-definition createUser
node build/cli.js impact src/queue.ts
node build/cli.js export-mermaid calls --out call-graph.mmdAdd to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json
on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"codegraph": {
"command": "node",
"args": ["/absolute/path/to/codegraph-mcp/build/mcpServer.js"]
}
}
}Or test directly without Claude Desktop using MCP Inspector:
npx @modelcontextprotocol/inspector node build/mcpServer.jsnpm run dev # run the CLI directly with tsx, no build step
npm test # full automated test suite against the fixture projectsrc/fileDiscovery.ts — walks the filesystem for source files, skipping
node_modules/build output/tests, with cross-platform path normalization
src/parser.ts — the core: builds a ts.Program, extracts every
function/method/class declaration, then resolves every call expression
and import specifier via the real type checker
src/graphStore.ts — persists the graph as JSON, not SQLite. Deliberate
tradeoff: a native SQLite binding needs platform-specific compilation
(node-gyp), which is exactly the kind of cross-platform friction this
project avoids. A repo-sized graph fits comfortably in memory as JSON —
SQLite would be the right upgrade for very large monorepos, not for this
scope.
src/queries.ts — builds in-memory indices (by id, by name, adjacency
lists) over the loaded graph and answers the actual questions
src/mermaid.ts — visual export for human inspection
src/mcpServer.ts — wraps the query engine as MCP tools
src/cli.ts — same functionality as a standalone command-line tool
Single-language scope. TypeScript/JavaScript only — not the 158 languages some production code-intelligence tools support. This is a focused demonstration of the technique, not a general-purpose tool.
Private class members (#method) aren't tracked yet. TypeScript's
private-field syntax uses a different AST node type than regular method
names; this project doesn't yet register or resolve calls to them.
Static analysis only. Dynamic dispatch (calling a function stored in a variable that could point at several different implementations) isn't resolved — only calls the type checker can statically determine.
JSON storage, not a real database. Fine at single-repo scale; wouldn't scale cleanly to a huge monorepo (see architecture notes above).
Support private class members (#foo) as trackable symbols
Incremental re-indexing (only re-parse changed files) instead of a full rebuild every time
A small web UI rendering the Mermaid export interactively instead of static text
MIT
Find every function/method called from within a given symbol.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol_id | Yes | Exact symbol id from find_definition | |
| graph_path | No | Path to a previously saved graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states what the tool finds but not whether the search is direct or transitive, what the output format is, or whether it reads from the graph without modification. This leaves significant ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The entire description is a single, focused sentence with no unnecessary words. It is appropriately front-loaded and easily parseable by an agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should at least hint at the return structure. It does not. Although the params are well-documented, the tool lacks a full behavioral contract, making it adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter having a description, including the requirement that symbol_id is an exact symbol id from find_definition. The description adds no additional parameter information, so the schema itself does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function (find callees) with a specific verb and resource. It distinguishes from siblings like find_callers, which would be the inverse operation. The phrasing 'from within a given symbol' directly conveys the scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like find_callers or get_file_dependencies. The description does not mention that symbol_id should come from find_definition, although the schema does. No exclusions or comparisons provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find every function/method that calls a given symbol, resolved via the real TypeScript type checker (handles cross-file calls correctly, not just same-file text matches). Use find_definition first to get the exact symbol id.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol_id | Yes | Exact symbol id from find_definition, e.g. 'userService.ts#createUser#10' | |
| graph_path | No | Path to a previously saved graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It mentions the use of the real TypeScript type checker and correct cross-file handling, which is helpful, but it omits details about return format, error cases, or performance costs, leaving some ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, both earning their place. The primary action is front-loaded, and the second sentence provides a necessary usage hint without redundancy. No filler words or circular phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema, the description adequately conveys the outcome (list of callers) and the prerequisite workflow. Given the moderate complexity, it is sufficiently complete for an agent to invoke correctly, though it could mention the exact return structure without harming the score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions, so the baseline is 3. The description adds practical context by emphasizing that symbol_id must come from find_definition, which reinforces the schema and aids correct invocation, but it does not add new meaning beyond that.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action with a specific verb and resource: 'Find every function/method that calls a given symbol.' It also distinguishes the tool from the sibling find_callees (which finds the opposite direction) and the cross-file correctness adds meaningful context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use find_definition first to obtain the exact symbol id, providing a clear prerequisite. It implies superiority over text-matching searches but does not list when-not-to-use alternatives. The guidance is practical and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find the file and line where a function, method, or class is defined, by name.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Symbol name, e.g. 'createUser' or 'UserRepository.findById' | |
| graph_path | No | Path to a previously saved graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool returns a file and line, and that it operates by symbol name. However, it does not cover behavior for missing symbols, whether the graph must be indexed, or how multiple matches are handled.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that front-loads the main purpose and includes the key output details. No filler or redundant content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple lookup tool, the description states the essential return value (file and line) and the schema covers the parameters. It lacks explicit return format or edge-case handling, but the tool's simplicity makes this adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already covers 100% of the parameters, including an example with dotted paths. The description only adds the symbol types (function, method, class) and does not provide additional parameter semantics beyond what the schema gives.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool finds the file and line for a function, method, or class definition by name. This verb+resource phrasing distinguishes it from sibling tools like find_callers and find_callees, which focus on call relationships.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when a definition location is needed, but it does not explicitly mention alternatives or when to prefer this over siblings like find_callers or impact_analysis. There is no exclusion or comparison context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show what a file imports, and what imports that file, directly (one hop).
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Relative file path as it appears in the graph, e.g. 'src/userService.ts' | |
| graph_path | No | Path to a previously saved graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of disclosing behavior. It does state the one-hop, bidirectional nature, but it omits important behavioral context such as prerequisites (e.g., a previously saved graph), error behavior when the file is not found, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler. It efficiently conveys the tool's purpose and the one-hop constraint, earning the maximum score for conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately conveys the core return value (incoming and outgoing direct imports), but it is missing important context about the graph_path parameter and prerequisites. Since there is no output schema, a bit more detail about result structure would improve completeness, though the tool is relatively simple.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents both file_path and graph_path. The description adds no extra parameter meaning beyond referring to a 'file', which earns the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Show') and identifies the exact resource ('a file's direct import relationships'), including both directions (what it imports and what imports it). The 'one hop' qualifier clearly differentiates this from transitive dependency tools like impact_analysis.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to use this tool versus its siblings (e.g., find_callers, impact_analysis). The 'directly (one hop)' comment implies scope but does not explicitly name alternatives or exclusion conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Summary stats: file/symbol/edge counts, most-called functions, most-depended-on files.
| Name | Required | Description | Default |
|---|---|---|---|
| graph_path | No | Path to a previously saved graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits itself. It does not state that the operation is read-only, whether an existing graph is required, or how it behaves if the graph file is missing. The description only lists return content, not side effects or prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that immediately communicates the tool's output with specific examples. It is well-structured and avoids any unnecessary words, making it highly concise and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one optional parameter, but the description lacks important context such as prerequisites (e.g., graph must already exist), output format, and explicit usage scenarios. The schema and sibling tool names provide some context, making it minimally complete but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides full coverage for graph_path with its description and default value, so the tool description does not need to elaborate. The description adds no parameter semantics beyond the schema, which is expected given 100% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns summary statistics including file/symbol/edge counts and most-called/depended-on items. This distinguishes it from sibling tools like find_definition and find_callers, which focus on specific queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for high-level overview of the codebase graph, but it does not explicitly state when to use it over the sibling tools, nor does it mention prerequisites like running index_codebase first. No alternatives or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find every file that transitively depends on a given file, directly or indirectly, up to a depth limit. Answers 'what could break if I change this file' — the main practical use case for an AI agent about to edit code.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Relative file path to analyze | |
| max_depth | No | How many hops to follow (default 5) | |
| graph_path | No | Path to a previously saved graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It explains the traversal semantics (direct or indirect, depth-limited) and the intent, but doesn't disclose whether the operation is read-only, requires a pre-built graph, or any edge-case behavior. This leaves some gaps in behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the action, and the second sentence adds practical context. No verbosity or unrelated details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description effectively communicates the purpose and main use case for a graph traversal tool. However, it omits the dependency on an existing graph file and doesn't describe the output structure, which are notable for an agent expecting to use the result in an edit workflow. Given the schema is rich, the description is mostly complete but has those gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage of all three parameters with descriptions, so the description adds little beyond what the schema already provides. The description's mention of 'depth limit' aligns with max_depth, and 'given file' with file_path, but no new parameter-specific semantics are introduced.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Find') and resource ('file') and explicitly states the transitive, indirect nature with depth limit. It distinguishes itself from sibling tools like find_callers/find_callees by focusing on transitive dependencies, and ties to a concrete use case ('what could break if I change this file').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It clearly states the primary use case for an AI agent about to edit code, giving explicit when-to-use context. However, it does not explicitly name alternatives or when not to use it, which limits full differentiation from sibling tools like find_callers or get_file_dependencies.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse a TypeScript/JavaScript codebase into a call graph and import graph, using the real TypeScript type checker for symbol resolution (not regex matching). Run this first before using any query tool.
| Name | Required | Description | Default |
|---|---|---|---|
| root_dir | Yes | Absolute path to the codebase root to index | |
| graph_path | No | Where to save the resulting graph (default: .codegraph/graph.json) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden. It discloses a key behavioral trait: using the real TypeScript type checker rather than regex matching, which indicates accuracy. However, it does not mention side effects like writing a graph file (though implied by graph_path) or potential performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loaded with the core purpose and method. The usage guideline is placed at the end, but the entire text is efficient with no filler words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with only 2 params and no output schema, the description covers the essential purpose, methodology, and usage order. It doesn't explain the resulting graph's format or return behavior, but the schema's graph_path parameter already hints at the output file, and query tools are expected to consume it. Adequate for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% — both root_dir and graph_path have descriptions in the input schema. The tool description adds no additional semantic meaning beyond what the schema already provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool parses a TypeScript/JavaScript codebase into call and import graphs, with a specific verb ('Parse') and resource (codebase). It distinguishes itself from siblings by positioning it as the prerequisite step before query tools, which are all about querying existing graphs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Run this first before using any query tool,' providing clear usage context and ordering. It implies when not to use it (for answering queries) but does not name alternative tools explicitly; the sibling list makes that implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0find_calleesfind_callersfind_definitionget_file_dependenciesget_graph_summaryimpact_analysisindex_codebaseEach tool addresses a distinct aspect of code graph analysis: initialization, definition lookup, forward/reverse call relationships, direct file dependencies, transitive impact, and summary statistics. There is no overlap between find_callers, find_callees, and impact_analysis, as each operates at a different level of granularity or direction.
Most tools follow a clear verb_noun pattern (index_codebase, find_definition, find_callers, find_callees, get_file_dependencies, get_graph_summary), but impact_analysis breaks the convention as a compound noun rather than an imperative verb phrase. The consistency is strong overall.
Seven tools is a well-scoped count for a code graph server. Each tool covers a necessary capability without redundancy, making the set feel complete and manageable.
The tool surface covers the full lifecycle of code graph exploration: building the graph, finding definitions, traversing callers/callees, examining file dependencies, performing transitive impact analysis, and obtaining summary stats. There are no obvious dead ends or missing core operations.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted code graph over MCP: exact callers, dependencies, and cross-repo blast radius for AI agents.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
An MCP server that provides congressional transcripts
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SiwarKhalfaoui/codegraph-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
